< Prev | Home | Model | Random | Next >

Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 46 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')



Text #0

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.3625. Min Act: -0.0001

Data Index: 1904151 (The Pile)

Max Activating Token Index: 201

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2669. Min Act: -0.0001

Data Index: 1269637 (The Pile)

Max Activating Token Index: 442

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2508. Min Act: -0.0001

Data Index: 1098915 (The Pile)

Max Activating Token Index: 35

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2547. Min Act: -0.0001

Data Index: 932576 (The Pile)

Max Activating Token Index: 110

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2524. Min Act: -0.0001

Data Index: 644521 (The Pile)

Max Activating Token Index: 126

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2420. Min Act: -0.0001

Data Index: 1161859 (The Pile)

Max Activating Token Index: 811

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2549. Min Act: -0.0001

Data Index: 1133441 (The Pile)

Max Activating Token Index: 695

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2296. Min Act: -0.0001

Data Index: 1482782 (The Pile)

Max Activating Token Index: 925

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2256. Min Act: -0.0001

Data Index: 768787 (The Pile)

Max Activating Token Index: 104

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2374. Min Act: -0.0001

Data Index: 269689 (The Pile)

Max Activating Token Index: 141

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2222. Min Act: -0.0001

Data Index: 362973 (The Pile)

Max Activating Token Index: 410

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2206. Min Act: -0.0001

Data Index: 1327052 (The Pile)

Max Activating Token Index: 419

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2190. Min Act: -0.0001

Data Index: 499378 (The Pile)

Max Activating Token Index: 689

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2126. Min Act: -0.0001

Data Index: 93440 (The Pile)

Max Activating Token Index: 485

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2313. Min Act: -0.0001

Data Index: 848082 (The Pile)

Max Activating Token Index: 650

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2223. Min Act: -0.0001

Data Index: 1981121 (The Pile)

Max Activating Token Index: 920

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2297. Min Act: -0.0001

Data Index: 123804 (The Pile)

Max Activating Token Index: 872

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2098. Min Act: -0.0001

Data Index: 1332395 (The Pile)

Max Activating Token Index: 76

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2138. Min Act: -0.0001

Data Index: 1346119 (The Pile)

Max Activating Token Index: 554

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2066. Min Act: -0.0001

Data Index: 752352 (The Pile)

Max Activating Token Index: 341

Click toggle to see full text

Truncated

Full Text #19